A Runway Overrun Risk Assessment Model for Civil Aircraft Based on Quick Access Recorder Data
Source abstract
Abstract
The quick access recorder (QAR), as an airborne device used to monitor and record flight parameters, has been widely installed on various types of aircraft. Based on QAR data, research on runway overrun, a typical flight safety incident, has attracted widespread attention in recent years. However, existing runway overrun risk models generally suffer from oversimplified risk metrics or insufficient consideration of risk dynamics. In this paper, we propose a new dynamic runway overrun risk assessment model based on QAR data. We first consider the noise of aircraft trajectory data in the QAR parameters and present a landing trajectory correction method combining ground speed and runway position information. Second, to improve the accuracy of the risk assessment model, we design an algorithm to automatically recognize the aircraft autobrake level during the landing phase, based on which a new dynamic risk assessment model is developed. Finally, feature engineering is performed to extract the relevant contributing factors of runway overrun risk, based on which classification and regression models are applied to identify risky flights and predict the risk values. The proposed risk assessment model was evaluated using QAR data from an airline in China. The results show that the automatic deceleration rate, the way that the aircraft approaches the runway, the touchdown distance, and the kinetic energy at 50 ft are key factors in the risk of runway overrun during the landing phase.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Air Traffic Management and Optimization · Aerospace and Aviation Technology · Traffic and Road Safety
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Guanghan Branch, Civil Aviation Flight University of China, Guanghan 618307, China
School of Flight Technology, Civil Aviation Flight University of China, Guanghan 618307, China
College of Computer Science, Chongqing University, Chongqing 400044, China
Key Laboratory of Dependable Service Computing in Cyber Physical Society, Ministry of Education, Chongqing University, Chongqing 400044, China
Funding
National Key Research and Development Program of China · National Natural Science Foundation of China · Safety ability Foundation of Civil Aviation Administration of China · Civil Aviation Flight Technology and Flight Safety Key Laboratory Foundation · Open Fund of Key Laboratory of Flight Techniques and Flight Safety, and CAAC
References (38)
Show source-provided references
1. Lu, X., Chen, D., and Zhang, F. (2019, January 17–19). Grey correlation analysis of hard landing based on QAR data. Proceedings of the 2019 IEEE 1st International Conference on Civil Aviation Safety and Information Technology (ICCASIT), Kunming, China.10.1109/ICCASIT48058.2019.8973163 ↗
2. Xie, J., Sun, H., Jiao, Y., and Lu, B. (2019, January 17–19). Association rules mining with QAR data: An analysis on unstable approaches. Proceedings of the 2019 IEEE 1st International Conference on Civil Aviation Safety and Information Technology (ICCASIT), Kunming, China.10.1109/ICCASIT48058.2019.8973217 ↗
3. Boeing, C.A. (2021, October 01). Statistical Summary of Commercial Jet Airplane Accidents-Worldwide Operations 1959–2018. Available online: http://www.boeing.com/news/techissues.
4. IATA (2015). IATA Runway Safety Accident Analysis Report 2010–2014, IATA.
5. Memarzadeh, M., Matthews, B., and Avrekh, I. (2020). Unsupervised anomaly detection in flight data using convolutional variational auto-encoder. Aerospace, 7.10.3390/aerospace7080115 ↗
6. Using machine learning methods in airline flight data monitoring to generate new operational safety knowledge from existing data10.1016/j.ssci.2018.12.018 ↗
7. Multiclass Anomaly Detection in Flight Data Using Semi-Supervised Explainable Deep Learning Model
8. The normalisation of aircraft overrun accident data10.1016/S0969-6997(03)00033-4 ↗
9. An improved methodology for assessing risk in aircraft operations at airports, applied to runway overruns10.1016/j.ssci.2004.04.002 ↗
10. The development of probabilistic models to estimate accident risk (due to runway overrun and landing undershoot) applicable to the design and construction of runway safety areas10.1016/j.ssci.2010.09.020 ↗
11. Modelling the location and consequences of aircraft accidents10.1016/j.ssci.2012.05.012 ↗
12. Statistical methods for modeling the risk of runway excursions10.1080/13669877.2013.822913 ↗
13. Wang, L., Wu, C., and Sun, R. (2013, January 21–26). Pilot operating characteristics analysis of long landing based on flight QAR data. Proceedings of the Engineering Psychology and Cognitive Ergonomics. Applications and Services: 10th International Conference, EPCE 2013, Held as Part of HCI International 2013, Las Vegas, NV, USA. Proceedings, Part II 10.
14. An analysis of flight Quick Access Recorder (QAR) data and its applications in preventing landing incidents10.1016/j.ress.2014.03.013 ↗
15. Wang, L., Ren, Y., Sun, H., and Dong, C. (2017, January 9–14). A landing operation performance evaluation system based on flight data. Proceedings of the Engineering Psychology and Cognitive Ergonomics: Cognition and Design: 14th International Conference, EPCE 2017, Held as Part of HCI International 2017, Vancouver, BC, Canada. Proceedings, Part II 14.
16. A method of applying flight data to evaluate landing operation performance10.1080/00140139.2018.1502806 ↗
17. Kang, Z., Shang, J., Feng, Y., Zheng, L., Liu, D., Qiang, B., and Wei, R. (November, January 31). A Deep Sequence-to-Sequence Method for Aircraft Landing Speed Prediction Based on QAR Data. Proceedings of the International Conference on Web Information Systems Engineering, Biarritz, France.
18. A deep sequence-to-sequence method for accurate long landing prediction based on flight data10.1049/itr2.12078 ↗
19. Lv, H., Yu, J., and Zhu, T. (2018, January 26–29). A novel method of overrun risk measurement and assessment using large scale QAR data. Proceedings of the 2018 IEEE Fourth International Conference on Big Data Computing Service and Applications (BigDataService), Bamberg, Germany.10.1109/BigDataService.2018.00039 ↗
20. Bayesian network for managing runway overruns in aviation safety
21. Koppitz, P., Wang, C., Höhndorf, L., Sembiring, J., Wang, X., and Holzapfel, F. (2019, January 6–9). From raw operational flight data to incident probabilities using subset simulation and a complex thrust model. Proceedings of the AIAA Scitech 2019 Forum, San Diego, CA, USA.10.2514/6.2019-2233 ↗
22. Safety risk analysis in flight operations quality assurance10.1016/j.sepro.2012.04.013 ↗
23. Liu, S., Zhang, Y., and Chen, J. (2018, January 15–20). A system for evaluating pilot performance based on flight data. Proceedings of the Engineering Psychology and Cognitive Ergonomics: 15th International Conference, EPCE 2018, Held as Part of HCI International 2018, Las Vegas, NV, USA. Proceedings 15.
24. Wang, L., Zhang, J., Sun, H., and Ren, Y. (2018, January 15–20). Risk cognition variables and flight exceedance behaviors of airline transport pilots. Proceedings of the Engineering Psychology and Cognitive Ergonomics: 15th International Conference, EPCE 2018, Held as Part of HCI International 2018, Las Vegas, NV, USA. Proceedings 15.
25. Li, X., Qian, Y., Chen, H., Zheng, L., Wang, Q., and Shang, J. (2022). An Unsupervised Learning Approach for Analyzing Unsafe Pilot Operations Based on Flight Data. Appl. Sci., 12.10.3390/app122412789 ↗
26. Hu, C., Zhou, S.H., Xie, Y., and Chang, W.B. (2016, January 27–29). The study on hard landing prediction model with optimized parameter SVM method. Proceedings of the 2016 35th Chinese Control Conference (CCC), Chengdu, China.10.1109/ChiCC.2016.7554018 ↗
27. Qiao, X., Chang, W., Zhou, S., and Lu, X. (2016, January 4–7). A prediction model of hard landing based on RBF neural network with K-means clustering algorithm. Proceedings of the 2016 IEEE International Conference on Industrial Engineering and Engineering Management (IEEM), Bali, Indonesia.10.1109/IEEM.2016.7797918 ↗
28. An innovative deep architecture for aircraft hard landing prediction based on time-series sensor data10.1016/j.asoc.2018.07.061 ↗
29. A novel deep learning method for aircraft landing speed prediction based on cloud-based sensor data10.1016/j.future.2018.06.023 ↗
30. Chen, R., and Jin, J. (2021, January 11–13). Detection of Influential Features of Hard Landing Based on QAR Data. Proceedings of the 2021 IEEE 3rd International Conference on Civil Aviation Safety and Information Technology (ICCASIT), Dali, China.10.1109/ICCASIT53235.2021.9633658 ↗
31. Li, X., Shang, J., Zheng, L., Liu, D., Qi, L., and Liu, L. (2019, January 19–23). CurveCluster: Automated recognition of hard landing patterns based on QAR curve clustering. Proceedings of the IEEE International Conference on Ubiquitous Intelligence and Computing, Leicester, UK.10.1109/SmartWorld-UIC-ATC-SCALCOM-IOP-SCI.2019.00141 ↗
32. Curvecluster+: Curve clustering for hard landing pattern recognition and risk evaluation based on flight data10.1109/TITS.2021.3117846 ↗
33. Chen, H., Shang, J., Zheng, L., Li, X., Liu, X., Sun, H., Zhao, X., and Yu, L. (2023). SDTAN: Scalable Deep Time-Aware Attention Network for Interpretable Hard Landing Prediction. IEEE Trans. Intell. Transp. Syst.10.1109/TITS.2023.3267035 ↗
34. Jin, J., Yan, J., and Chen, K. (2022). Transfer learning with quantile regression. arXiv.
35. Li, L., Gariel, M., Hansman, R.J., and Palacios, R. (2011, January 16–20). Anomaly detection in onboard-recorded flight data using cluster analysis. Proceedings of the 2011 IEEE/AIAA 30th Digital Avionics Systems Conference, Seattle, WA, USA.10.1109/DASC.2011.6096068 ↗
36. Das, S., Li, L., Srivastava, A., and Hansman, R.J. (2012, January 17–19). Comparison of algorithms for anomaly detection in flight recorder data of airline operations. Proceedings of the 12th AIAA Aviation Technology, Integration, and Operations (ATIO) Conference and 14th AIAA/ISSMO Multidisciplinary Analysis and Optimization Conference, Indianapolis, IN, USA.10.2514/6.2012-5593 ↗
37. Analysis of flight data using clustering techniques for detecting abnormal operations
38. Anomaly detection via a Gaussian Mixture Model for flight operation and safety monitoring10.1016/j.trc.2016.01.007 ↗